# Gemini 3.8 text-to-speech models now available on AI Gateway

Source: [Vercel](https://vercel.com/changelog/gemini-3-8-text-to-speech-models-now-available-on-ai-gateway)  
Feed7 permalink: https://feed7.dev/p/gemini-3-8-text-to-speech-models-now-available-on-ai-gateway-1ur27ch  
Published: 2026-09-23T00:00:00.000Z  
Trust: Official Source (official_source)

## Why Included

Vercel AI Gateway now exposes two Gemini 3.8 TTS models for multilingual speech, separating high-volume generation from prompt-driven voice design.

## Source Summary

AI Gateway now offers **Gemini 3.8 Flash-Lite TTS** and **Gemini 3.8 Flash TTS**. Both generate speech in **more than 100 languages** and support long narration and two-speaker dialogue.

## Practical Implication

Use Flash-Lite for high-volume output with tone, pacing, and line-level controls. Choose Flash when an agent needs prompt-driven voice or character design, including acting cues, accents, and reactions.

## Agent-Ready Context

AI Gateway now offers **Gemini 3.8 Flash-Lite TTS** and **Gemini 3.8 Flash TTS**. Both generate speech in **more than 100 languages** and support long narration and two-speaker dialogue.

Use Flash-Lite for high-volume output with tone, pacing, and line-level controls. Choose Flash when an agent needs prompt-driven voice or character design, including acting cues, accents, and reactions.

The material describes capabilities and gateway features such as routing, request-level usage tracking, and provider keys, but provides no pricing, latency, quality evaluation, or language-by-language results.

## Connected Context

Feed7 judgment across 875 accumulated Signals:

This turns the Gateway’s audio offering into a clearer output-side choice: Flash-Lite targets controlled volume production, while Flash targets prompt-shaped performance and character work. It complements existing transcription routes and overlaps Fish Audio’s speech generation, but the supplied record still supports only integration-level evaluation—not a quality, latency, or cost preference.

- [Fish Audio models now available on Vercel AI Gateway for free](https://feed7.dev/p/fish-audio-models-now-available-on-ai-gateway-for-free-0rw6kco) — Fish Audio is the closest existing speech-generation route, so Gemini 3.8 creates a direct workload-specific alternative while lacking the temporary free-path and billing behavior documented for Fish.
- [Gemini 3.5 Transcribe now available on AI Gateway](https://feed7.dev/p/gemini-3-5-transcribe-now-available-on-ai-gateway-08us8jk) — Gemini 3.5 Transcribe supplies the voice-input side that these TTS models lack, making the two signals complementary components for multilingual conversational audio pipelines.

## Context Map

- Layer: infra
- Domains: audio
- Topics: generative-media, gateways, model-selection

## Uncertainty

- The material describes capabilities and gateway features such as routing, request-level usage tracking, and provider keys, but provides no pricing, latency, quality evaluation, or language-by-language results.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.